text-based games
31 papers with code • 0 benchmarks • 3 datasets
Text-based games to evaluate the Reinforcement Learning Agents
Benchmarks
These leaderboards are used to track progress in text-based games
Libraries
Use these libraries to find text-based games models and implementations
Jericho
TextWorld KG
Cards Against Humanity
Most implemented papers
How To Avoid Being Eaten By a Grue: Exploration Strategies for Text-Adventure Agents
We compare our exploration strategies against strong baselines on the classic text-adventure game, Zork1, where prior agent have been unable to get past a bottleneck where the agent is eaten by a Grue.
Learning Dynamic Belief Graphs to Generalize on Text-Based Games
xingdi-eric-yuan/GATA-public
•
•
NeurIPS 2020
Playing text-based games requires skills in processing natural language and sequential decision making.
How to Avoid Being Eaten by a Grue: Structured Exploration Strategies for Textual Worlds
Text-based games are long puzzles or quests, characterized by a sequence of sparse and potentially deceptive rewards.
Bootstrapped Q-learning with Context Relevant Observation Pruning to Generalize in Text-based Games
IBM/context-relevant-pruning-textrl
•
•
EMNLP 2020
Our bootstrapped agent shows improved generalization in solving unseen TextWorld games, using 10x-20x fewer training games compared to previous state-of-the-art methods despite requiring less number of training episodes.
Keep CALM and Explore: Language Models for Action Generation in Text-based Games
princeton-nlp/calm-textgame
•
•
EMNLP 2020
In this paper, we propose the Contextual Action Language Model (CALM) to generate a compact set of action candidates at each game state.
Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games
YunqiuXu/SHA-KG
•
•
NeurIPS 2020
We study reinforcement learning (RL) for text-based games, which are interactive simulations in the context of natural language.
Pre-trained Language Models as Prior Knowledge for Playing Text-based Games
Exploration-Lab/IFG-Pretrained-LM
•
•
Given the sample-inefficiency of RL approaches, it is inefficient to learn rich enough textual representations to be able to understand and reason using the textual observation in such a complicated game environment setting.
Generalization in Text-based Games via Hierarchical Reinforcement Learning
yunqiuxu/h-kga
•
•
Findings (EMNLP) 2021
Deep reinforcement learning provides a promising approach for text-based games in studying natural language communication between humans and artificial agents.
LOA: Logical Optimal Actions for Text-based Interaction Games
We present Logical Optimal Actions (LOA), an action decision architecture of reinforcement learning applications with a neuro-symbolic framework which is a combination of neural network and symbolic knowledge acquisition approach for natural language interaction games.
Perceiving the World: Question-guided Reinforcement Learning for Text-based Games
yunqiuxu/qwa
•
•
ACL 2022
Text-based games provide an interactive way to study natural language processing.
